In the paper we present a design strategy, current activities and some results of a joint project in development of a spoken dialog system for Slovenian and Croatian weather forecasts. We give a brief description of system design, procedures we have performed in order to obtain domain specific speech databases and monolingual and bilingual speech recognition experiments. Recognition results for Croatian and Slovenian speech are presented, as well as bilingual speech recognition results when using common acoustic models. We propose two different approaches to the language identification problem and show recognition results for the two acoustically similar languages like Slovenian and Croatian. We describe the software tools we have used for speech database design as well as tools for acoustic and language modelling.
展开▼
